- Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
2023/11/06 by Le Yu, Yu, Le, Bowen Yu +7 · 1 voice · 187 citations
Computer Science · #Algorithm #Artificial intelligence #Computer science #Encoder #Language model #Merge (version control) #Natural Language Processing Techniques #Parallel computing #Speech Recognition and Synthesis #Topic Modeling #cs.CL #cs.LG
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters
2023/11/06 by Ying Sheng, Sheng, Ying, Shiyi Cao +21 · 2 voices · 42 citations
Computer Science · #Adapter (computing) #Advanced Neural Network Applications #CUDA #Cache #Computer network #Computer science #Operating system #Overhead (engineering) #Paging #Parallel Computing and Optimization Techniques #Parallel computing #Scalability #Topic Modeling
- Optimizing Datalog for the GPU
2023/11/03 by Yihao Sun, Sun, Yihao, Ahmedur Rahman Shovon +7 · 4 voices
Computer Science · #Advanced Database Systems and Queries #Analytics #Computer science #Data Management and Algorithms #Data Mining Algorithms and Applications #Database #Datalog #Hash function #Information retrieval #Joins #Parallel computing #Programming language #SIMD #Search engine indexing #cs.DB #cs.PL
- On the accuracy and efficiency of group-wise clipping in differentially private optimization
2023/10/30 by Zhiqi Bu, Ruixuan Liu, Bu, Zhiqi +7 · 1 citation
Computer Science · #Algorithm #Clipping (morphology) #Computational Complexity (cs.CC) #Computer science #Convergence (economics) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Granularity #Key (lock) #Layer (electronics) #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and ELM #Materials science #Parallel computing #Speedup #Stochastic Gradient Optimization Techniques
- Efficient Parallelization of a Ubiquitous Sequential Computation
2023/10/27 by Franz A. Heinsen, Heinsen, Franz A. · 1 voice · 1 citation
Computer Science · Mathematics · #Algorithm #Algorithms and Data Compression #Combinatorics #Computation #Computer science #Discrete mathematics #Mathematics #Numerical Methods and Algorithms #Operating system #Parallel Computing and Optimization Techniques #Parallel algorithm #Parallel computing #Prefix #Sequence (biology) #Space (punctuation) #cs.DS #cs.LG
- QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
2023/10/25 by Elias Frantar, Dan Alistarh, Frantar, Elias +1 · 3 voices · 10 citations
Computer Science · #Algorithm #Artificial intelligence #Code (set theory) #Computer engineering #Computer hardware #Computer science #Decoding methods #Inference #Machine Learning and Algorithms #Operating system #Overhead (engineering) #Parallel computing #Programming language #Scalability #Speech Recognition and Synthesis #Topic Modeling #Uncompressed video #cs.LG
- HyperAttention: Long-context Attention in Near-Linear Time
2023/10/09 by In‐Su Han, Insu Han, Rajesh Jayaram +10 · 1 voice · 24 citations
Computer Science · Mathematics · #Advanced Neural Network Applications #Algorithm #Artificial intelligence #Computer science #Context (archaeology) #Domain Adaptation and Few-Shot Learning #Hash function #Inference #Mathematics #Matrix (chemical analysis) #Matrix completion #Multimodal Machine Learning Applications #Parallel computing #Quadratic equation #Rank (graph theory) #Speedup #Theoretical computer science #Time complexity #cs.AI #cs.LG
- Efficient Streaming Language Models with Attention Sinks
2023/09/29 by Guangxuan Xiao, Xiao, Guangxuan, Yuandong Tian +7 · 5 voices · 645 citations
Computer Science · #Algorithm #Artificial intelligence #Cache #Computer network #Computer science #Decoding methods #Language model #Natural Language Processing Techniques #Parallel computing #Security token #Sequence (biology) #Sink (geography) #Sliding window protocol #Speech Recognition and Synthesis #Speedup #Topic Modeling #Window (computing) #World Wide Web
- SIMD Everywhere Optimization from ARM NEON to RISC-V Vector Extensions
2023/09/28 by Ju-Hung Li, Jocelyn Li, Li, Ju-Hung +15 · 2 voices · 2 citations
Computer Science · #Code (set theory) #Compiler #Computer science #Intrinsics #Overhead (engineering) #Parallel Computing and Optimization Techniques #Parallel computing #Programming language #SIMD #Security and Verification in Computing #Set (abstract data type) #Software #Software Testing and Debugging Techniques #Solver #Speedup #Vectorization (mathematics) #cs.DC #cs.PL #x86
- Julia as a unifying end-to-end workflow language on the Frontier exascale system
2023/09/19 by William F. Godoy, Pedro Valero‐Lara, Pedro Valero-Lara +5 · 2 voices · 1 citation
Computer Science · Decision Sciences · #Advanced Data Storage Technologies #Computational science #Computer science #Database #Distributed and Parallel Computing Systems #Kernel (algebra) #Operating system #Parallel computing #Scientific Computing and Data Management #Stencil #Supercomputer #Workflow
- Efficient Memory Management for Large Language Model Serving with PagedAttention
2023/09/12 by Woosuk Kwon, Zhuohan Li, Kwon, Woosuk +15 · 4 voices · 2351 citations
Computer Science · #CPU cache #Cache #Cache algorithms #Cache coloring #Cache pollution #Caching and Content Delivery #Computer network #Computer science #Demand paging #Latency (audio) #Memory management #Operating system #Overlay #Page cache #Paging #Parallel computing #Software System Performance and Reliability #Topic Modeling #Virtual memory #cs.DC #cs.LG
- Large Language Models for Compiler Optimization
2023/09/11 by Chris Cummins, Volker Seeker, Cummins, Chris +20 · 2 voices · 22 citations
Computer Science · #Artificial intelligence #Code (set theory) #Code generation #Compiler #Computer science #Language model #Machine learning #Operating system #Optimizing compiler #Parallel Computing and Optimization Techniques #Parallel computing #Program optimization #Programming language #Scratch #Set (abstract data type) #Software Engineering Research #Software Testing and Debugging Techniques #Suite #Test case #Test suite #Transformer #cs.AI #cs.CL #cs.LG #cs.PL
- Serial and parallel kernelization of Multiple Hitting Set parameterized by the Dilworth number, implemented on the GPU
2023/09/12 by René van Bevern, Artem M. Kirilin, Daniel A. Skachkov +3 · 1 citation
Computer Science · Mathematics · #Algorithms and Data Compression #Combinatorics #Complexity and Algorithms in Graphs #Computer science #Graph Theory and Algorithms #Kernelization #Mathematics #Parallel computing #Parameterized complexity #Programming language #Set (abstract data type) #Theoretical computer science
- C++ Design Patterns for Low-latency Applications Including High-frequency Trading
2023/09/08 by Paul Bilokon, Burak Gunduz, Bilokon, Paul +1 · 5 voices
Computer Science · Economics, Econometrics and Finance · #Advanced Data Storage Technologies #Algorithmic trading #Benchmarking #Business #Cache #Cloud Computing and Resource Management #Computer network #Computer science #Finance #High-frequency trading #Latency (audio) #Low latency (capital markets) #Marketing #Parallel Computing and Optimization Techniques #Parallel computing #Profitability index #Statistical arbitrage #Telecommunications #Trading strategy #cs.PF #q-fin.TR
- Are SNNs Truly Energy-efficient? - A Hardware Perspective
2023/09/06 by Abhiroop Bhattacharjee, Bhattacharjee, Abhiroop, Ruokai Yin +5 · 2 citations
Engineering · Neuroscience · #Advanced Memory and Neural Computing #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Benchmarking #Computer architecture #Computer engineering #Computer hardware #Computer science #Crossbar switch #Efficient energy use #Energy (signal processing) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices #Field-programmable gate array #Hardware acceleration #Inference #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #Operating system #Overhead (engineering) #Parallel computing #Spiking neural network
- Is RISC-V ready for HPC prime-time: Evaluating the 64-core Sophon SG2042 RISC-V CPU
2023/09/01 by Nick Brown, Maurice Jamieson, Joseph Lee +3 · 2 voices · 6 citations
Computer Science · #Advanced Data Storage Technologies #Computer science #Instruction set #Multi-core processor #Numerical Methods and Algorithms #Operating system #Parallel Computing and Optimization Techniques #Parallel computing #Reduced instruction set computing
- eGPU: A 750 MHz Class Soft GPGPU for FPGA
2023/07/17 by Martin Langhammer, Langhammer, Martin, George Constantinides +2 · 1 voice
Computer Science · #Compiler #Computer hardware #Computer science #Digital signal processing #Embedded Systems Design Techniques #Embedded system #Field-programmable gate array #Interconnection Networks and Systems #Multiprocessing #Operating system #Parallel Computing and Optimization Techniques #Parallel computing
- Matrix Multiplication Using Only Addition
2023/07/04 by Daniel Cussen, Jeffrey D. Ullman, Cussen, Daniel +1 · 1 voice
Computer Science · Mathematics · #Algorithm #Arithmetic #Chip #Computer science #Mathematics #Matrix (chemical analysis) #Matrix multiplication #Multiplication (music) #Multiplier (economics) #Parallel Computing and Optimization Techniques #Parallel computing #Physics #Quantum Computing Algorithms and Architecture #Quantum-Dot Cellular Automata #Scalar (mathematics) #Scalar multiplication #Speedup #Telecommunications #cs.DS
- How to compute a 256-bit elliptic curve private key with only 50 million Toffoli gates
2023/06/14 by Daniel Litinski, Litinski, Daniel · 1 voice · 11 citations
Computer Science · Engineering · #Algorithm #Computation #Computer engineering #Computer science #Embedded system #Gate count #Key (lock) #Neural Networks and Reservoir Computing #Optical Network Technologies #Parallel computing #Quantum #Quantum Computing Algorithms and Architecture #Quantum computer #Quantum gate #Quantum mechanics #Qubit #Theoretical computer science #Toffoli gate #quant-ph
- Invertible Bloom Lookup Tables with Less Memory and Randomness
2023/06/13 by Nils Fleischhacker, Kasper Green Larsen, Maciej Obremski +1 · 1 voice · 1 citation
Computer Science · Mathematics · #Bloom #Caching and Content Delivery #Computer science #Geology #Invertible matrix #Lookup table #Mathematics #Parallel computing #Programming language #Randomness #Recommender Systems and Techniques #Statistics
- Potential of the Julia Programming Language for High Energy Physics Computing
2023/06/06 by Jonas Nathanael Eschle, J. Eschle, T. Gal +25 · 3 voices · 1 citation
Computer Science · Physics and Astronomy · #Application programming interface #Code (set theory) #Computational Physics and Python Applications #Computer science #Distributed and Parallel Computing Systems #First-generation programming language #High-level programming language #Interface (matter) #Parallel computing #Particle physics theoretical and experimental studies #Programming language #Programming paradigm #Python (programming language) #Software engineering
- Minotaur: A SIMD-Oriented Synthesizing Superoptimizer
2023/05/31 by Zhengyang Liu, Stefan Mada, Liu, Zhengyang +3 · 2 voices · 7 citations
Computer Science · #Computer science #Cryptographic Implementations and Security #Integer (computer science) #Literal (mathematical logic) #Parallel Computing and Optimization Techniques #Parallel computing #Programming language #Representation (politics) #SIMD #Security and Verification in Computing #Software #Solver #Suite #cs.PL #x86
- Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
2023/05/23 by Hong Liu, Liu, Hong, Zhiyuan Li +8 · 7 voices · 71 citations
Computer Science · Mathematics · #Advanced Neural Network Applications #Algorithm #Applied mathematics #Artificial intelligence #Clipping (morphology) #Computer science #Convexity #Diagonal #FLOPS #Geometry #Hessian matrix #Language model #Mathematical optimization #Mathematics #Natural Language Processing Techniques #Order (exchange) #Overhead (engineering) #Parallel computing #Perplexity #Scalability #Topic Modeling
- Parallelizing Quantum-Classical Workloads: Profiling the Impact of Splitting Techniques
2023/05/11 by Tuhin Khare, Ritajit Majumdar, Khare, Tuhin +9 · 2 citations
Computer Science · #Cloud Computing and Resource Management #Cloud computing #Computer engineering #Computer science #Electrical engineering #Electronic circuit #FOS: Physical sciences #Operating system #Overhead (engineering) #Parallel Computing and Optimization Techniques #Parallel computing #Physics #Quantum #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph) #Quantum algorithm #Quantum circuit #Quantum computer #Quantum error correction #Qubit #Workload
- Analysis and Mitigation of Shared Resource Contention on Heterogeneous Multicore: An Industrial Case Study
2023/04/25 by Michael M. Hangartner Bechtel, Bechtel, Michael, Heechul Yun +1 · 1 citation
Computer Science · Engineering · #Augmented reality #CCD and CMOS Imaging Sensors #Cache #Cloud Computing and Remote Desktop Technologies #Computer science #Denial-of-service attack #Distributed computing #Embedded system #Engineering #FOS: Computer and information sciences #Human–computer interaction #IoT and Edge/Fog Computing #Latency (audio) #Multi-core processor #Operating system #Parallel computing #Performance (cs.PF) #Scheduling (production processes)
- Automated translation and accelerated solving of differential equations on multiple GPU platforms
2023/04/13 by Utkarsh Utkarsh, Valentin Churavy, Yingbo Ma +9 · 3 voices · 7 citations
Computer Science · #Advanced Data Storage Technologies #CUDA #Code (set theory) #Code generation #Compiler #Computational science #Computer science #Coprocessor #Differential equation #Distributed and Parallel Computing Systems #Operating system #Ordinary differential equation #Parallel Computing and Optimization Techniques #Parallel computing #Programming language #Software portability #Solver
- Countering the Path Explosion Problem in the Symbolic Execution of Hardware Designs
2023/04/11 by Kaki Ryan, Cynthia Sturton, Ryan, Kaki +1 · 3 citations
Computer Science · Engineering · #Algorithm #Computer science #Datapath #Embedded system #Field-programmable gate array #Formal Methods in Verification #Logic gate #Logic synthesis #Model checking #Modular design #Netlist #Parallel computing #Path (computing) #Programming language #Radiation Effects in Electronics #Register-transfer level #Software #Symbolic execution #VLSI and Analog Circuit Testing #Verilog
- TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings
2023/04/04 by Norman P. Jouppi, George Thomas Kurian, Jouppi, Norman P. +27 · 1 voice · 86 citations
Computer Science · Engineering · #Advanced Optical Network Technologies #Computer architecture #Computer science #Dataflow #Embedded system #Field-programmable gate array #Interconnection Networks and Systems #Modularity (biology) #PCI Express #Parallel computing #Photonic and Optical Devices #Supercomputer #cs.AI #cs.AR #cs.LG #cs.PF
- The Cyclic Diagnosability Of Hypercubes Under The PMC Model And The MM* Model
2023/03/27 by Hong Zhang, Shuming Zhou, Eddie Cheng · 1 citation
Computer Science · Engineering · Mathematics · #Algorithm #Combinatorics #Computer science #Graph #Hypercube #Interconnection Networks and Systems #Mathematics #Multiprocessing #Parallel computing #Programming language #Radiation Effects in Electronics #Set (abstract data type) #VLSI and Analog Circuit Testing #Vertex (graph theory)
- Computing and Compressing Electron Repulsion Integrals on FPGAs
2023/03/23 by Xin Wu, Wu, Xin, Tobias Kenter +7 · 1 citation
Computer Science · Engineering · #Advanced Data Storage Technologies #Algorithm #Artificial intelligence #Chemical Physics (physics.chem-ph) #Computation #Computational Physics (physics.comp-ph) #Computational science #Computer hardware #Computer science #Distributed #FOS: Computer and information sciences #FOS: Physical sciences #Field-programmable gate array #Gaussian #Hardware Architecture (cs.AR) #Lossy compression #Low-power high-performance VLSI design #Parallel #Parallel Computing and Optimization Techniques #Parallel computing #Performance (cs.PF) #Physics #Quantum mechanics #Stratix #Throughput #and Cluster Computing (cs.DC)
prev more